Seminario: “Urban Data Science: from big data to models” di Luca Pappalardo, Università di Pisa

Abstract: The availability of big geo-spatial mobility data in the urban environment (e.g., GPS traces, mobile phone records, geo-tagged social media posts) is a trend that will grow in the near future. In particular, this will happen when the shift from traditional vehicles to autonomous, self-driving, vehicles, will transform our society, the economy and the environment. For this reason, understanding and modeling urban mobility is of paramount importance for many present and future applications such as traffic forecasting and urban planning, epidemic modeling, and the design of new generation wireless mobile networks. During the talk I will present both the fundamental modeling principles of human mobility and artificial intelligence models applicable to specific mobility-related problems. In particular, starting from the "physical" laws that govern human mobility, we see how they can be exploited to address fascinating problems in urban data science, such as the generation of realistic synthetic mobility trajectories, and the prediction of the future locations visited by individuals.